© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 39203
    Prev
    Next
    INDEX
    Explanations

    symbols and annotations typically used in code documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ank
    -0.07
    lix
    -0.07
    .databinding
    -0.06
    ape
    -0.06
     Wer
    -0.06
     downs
    -0.05
    tec
    -0.05
     exactly
    -0.05
    myModal
    -0.05
    odia
    -0.05
    POSITIVE LOGITS
    /stdc
    0.08
    çĬ
    0.08
     ä»»
    0.07
    eniable
    0.07
    icher
    0.07
     COPYRIGHT
    0.07
    bbc
    0.07
    iyim
    0.07
     ëĭ¤ìļ´ë°Ľê¸°
    0.07
    uthor
    0.07
    Activations Density 0.008%

    No Known Activations